© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 18174
    Prev
    Next
    INDEX
    Explanations

    references to things being in the middle of a location or sequence

    oai_token-act-pair · gpt-3.5-turbo

    references to "the middle" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edIn
    -0.74
    itsch
    -0.72
    mbuds
    -0.70
    osponsors
    -0.67
    ilings
    -0.67
    orthy
    -0.67
    SIGN
    -0.66
    ESCO
    -0.66
     Gleaming
    -0.65
    untu
    -0.65
    POSITIVE LOGITS
    brow
    0.78
     layer
    0.78
     of
    0.75
     circle
    0.74
     innings
    0.73
     aisle
    0.73
     woods
    0.72
     lane
    0.71
     thereof
    0.70
     hallway
    0.68
    Activations Density 0.021%

    No Known Activations